INDEX

Explanations

words related to procedures or activities involving the brain

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'v' in words

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĪĴ

-0.91

¿½

-0.69

 mosqu

-0.68

¥µ

-0.65

 millenn

-0.65

 bumper

-0.64

dress

-0.64

Ĥª

-0.62

--------------------------------------------------------

-0.62

maid

-0.61

POSITIVE LOGITS

olution

1.13

ascular

1.13

irus

1.11

apor

1.09

irgin

1.07

intage

1.07

isions

1.05

endor

1.04

ampire

1.04

ault

1.03

Activations Density 0.039%

words related to procedures or activities involving the brain

occurrences of the letter 'v' in words

No Comments

No Known Activations